CN117890851A - Fault processing system applied to automatic detection line of intelligent ammeter - Google Patents
Fault processing system applied to automatic detection line of intelligent ammeter Download PDFInfo
- Publication number
- CN117890851A CN117890851A CN202410295705.4A CN202410295705A CN117890851A CN 117890851 A CN117890851 A CN 117890851A CN 202410295705 A CN202410295705 A CN 202410295705A CN 117890851 A CN117890851 A CN 117890851A
- Authority
- CN
- China
- Prior art keywords
- ammeter
- pose
- image information
- information
- tray
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 36
- 238000012545 processing Methods 0.000 title claims abstract description 36
- 230000000007 visual effect Effects 0.000 claims abstract description 38
- 238000012795 verification Methods 0.000 claims abstract description 22
- 239000011159 matrix material Substances 0.000 claims description 32
- 230000009466 transformation Effects 0.000 claims description 28
- 238000006243 chemical reaction Methods 0.000 claims description 27
- 238000000034 method Methods 0.000 claims description 20
- 239000013598 vector Substances 0.000 claims description 13
- 238000000605 extraction Methods 0.000 claims description 11
- 238000013500 data storage Methods 0.000 claims description 7
- 238000007689 inspection Methods 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 4
- 238000003708 edge detection Methods 0.000 claims description 4
- 238000013459 approach Methods 0.000 claims description 3
- 230000008859 change Effects 0.000 claims description 3
- 238000012804 iterative process Methods 0.000 claims description 3
- 230000009467 reduction Effects 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims 1
- 238000004519 manufacturing process Methods 0.000 abstract description 15
- 230000008569 process Effects 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 238000001914 filtration Methods 0.000 description 4
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 description 2
- 238000007476 Maximum Likelihood Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Manipulator (AREA)
Abstract
The invention provides a fault processing system applied to an automatic detection line of an intelligent ammeter, which belongs to the technical field of electric power meter detection and comprises the following components: the device comprises an ammeter detection line, a PLC industrial personal computer, a cooperative robot and a pneumatic clamping unit; a plurality of trays are arranged on the ammeter verification line, and a plurality of ammeter are placed on the trays; the cooperative robot is provided with a visual sensing unit; the PLC industrial personal computer controls the cooperative robot to drive the visual sensing unit to move above the verification position tray, and captures the overall image information of a plurality of electric meters on the tray, and judges whether the placing pose information of all the electric meters is matched with the placing pose information of each electric meter in a preset standard image; if the electric meters are not matched, the PLC industrial personal computer controls the pneumatic clamping unit to grab the unmatched electric meters and adjust the placing pose so as to meet production requirements, improve the working efficiency of the production line and ensure the production quality of the electric meters.
Description
Technical Field
The invention belongs to the technical field of electric power meter detection, and particularly relates to a fault processing system applied to an automatic detection line of an intelligent electric meter.
Background
With the continuous and deep intensive management of electric energy metering, the electric power metering verification work has greatly progressed, and the automatic verification of the electric energy meter is basically realized. In this process, the electric energy meter automation verification line is an important component of the metrological verification production, and the safe and efficient operation of the electric energy meter automation verification line is crucial to the production capacity and purchase distribution plan of the metrological verification. However, the stability of the automated inspection line is greatly affected by system failure. If these faults cannot be found and handled in time, they have a slight effect on the production, possibly even resulting in production stalls and thus in adverse effects on the subsequent steps of distribution, installation, etc.
The automatic detection line of the electric energy meter consists of a plurality of different devices, and the accurate positioning of faults and the timely treatment of the faults in a short time become difficult to realize due to the high integration property of the automatic detection line. The traditional method for monitoring the abnormality of the production process of the electric energy meter usually takes an acquisition module as a unit, only alarms and analyzes faults in a local range, and meanwhile, manual intervention is needed to carry and process the fault meter. The mode leads to lower fault positioning efficiency, limited equipment utilization rate and poor monitoring reliability, so that continuous and stable operation of an automatic detection line of the electric energy meter is difficult to ensure.
Disclosure of Invention
The invention provides a fault processing system applied to an automatic detection line of an intelligent ammeter, which can realize fault detection, ensure the safety of a production line, and greatly improve the working efficiency and the overall automation informatization level of the production line.
The system comprises: the device comprises an ammeter detection line, a PLC industrial personal computer, a cooperative robot and a pneumatic clamping unit;
a plurality of trays are arranged on the ammeter verification line, and a plurality of ammeter are placed on the trays; the electric meter verification line is provided with a detection position, and the cooperative robot and the pneumatic clamping unit are arranged close to the detection position;
the cooperative robot is provided with a visual sensing unit;
the PLC industrial personal computer is connected with the cooperative robot, controls the cooperative robot to drive the visual sensing unit to move above the verification position tray, controls the visual sensing unit to capture the whole image information of a plurality of electric meters on the tray, compares the placement pose information of each electric meter in the whole image information with the placement pose information of each electric meter in a preset standard image, and judges whether the placement pose information of all the electric meters is matched with the placement pose information of each electric meter in the preset standard image;
if the placing pose information of the electric meters is not matched, the PLC industrial personal computer controls the pneumatic clamping unit to grasp the unmatched electric meters, and adjusts the placing pose of the electric meters in the tray, so that the adjusted placing pose of the electric meters is matched with the preset placing pose information.
It should be further noted that the verification position is provided with a proximity switch;
the PLC industrial personal computer is connected with the proximity switch to acquire a trigger signal when the tray approaches the proximity switch, and controls the cooperative robot to drive the visual sensing unit to move to the position above the verification tray.
It should be further noted that, the cooperative robot perceives position information based on the point cloud data, and based on a control instruction of the PLC industrial personal computer, the visual sensing unit is controlled to be above the tray, and overall image information of a plurality of electric meters on the tray is captured.
It should be further noted that the visual sensing unit includes: 3D cameras and 2D cameras;
the 3D camera is used for shooting the whole image information of the plurality of ammeter on the tray, and the three-dimensional point cloud image is used as the whole image information;
the 2D camera is used for shooting upper surface image information of a plurality of ammeter on the tray.
The cooperative robot is provided with a mechanical arm, and the tail end of the mechanical arm is provided with a visual sensing unit and an attitude sensor;
the bottom of the cooperative robot is provided with a base;
the PLC industrial personal computer obtains pose coordinates according to a pose sensor at the tail end of the mechanical arm, converts the pose coordinates into a robot base coordinate system, and calibrates the coordinate system conversion relation as follows:
（1）
wherein,for visual sense unit to robot arm end conversion matrix, < >>For calibrating the conversion matrix of board to cooperation robot base, +.>To coordinate the robot base to robot arm tip conversion matrix,the matrix is a conversion matrix from the visual sensing unit to the calibration plate.
Further, the PLC industrial personal computer controls the cooperative robot to change the pose, so that the position and the pose of the cooperative robot are obtained:
(2)
(3)
calibrating the plate to the first time pointConversion matrix of base of cooperative robot, +.>Calibrating a conversion matrix from the plate to the base of the cooperative robot for a second time point; />For the transformation matrix from the first time point cooperation robot base to the tail end of the mechanical arm, < >>A conversion matrix from the base of the cooperative robot to the tail end of the mechanical arm is used for a second time point; />For the first time point the conversion matrix of the visual sensor unit to the calibration plate,/for the first time point the visual sensor unit to the calibration plate>And (3) converting the visual sensing unit to a calibration plate for a second time point.
It should be further noted that the PLC industrial personal computer includes: the device comprises a data acquisition module, a data processing module, a data storage module and a data display module;
the data acquisition module is used for acquiring image information of the upper surfaces of the plurality of ammeter on the 2D camera shooting tray;
the data processing module is used for sequentially carrying out image noise reduction, image enhancement and feature extraction on the upper surface image information;
extracting an LCD screen, signage characters, bar codes and LED indicator lamps of the ammeter;
the data processing module is used for respectively and correspondingly comparing the LCD screen, the signage characters, the bar codes and the LED indicator lamps of the ammeter with the image information of the standard ammeter to judge whether the images are matched;
the data storage module is used for storing the acquired upper surface image information, the standard ammeter image information and the comparison judgment information;
the data display module is used for displaying upper surface image information and comparison judgment information result information.
The feature extraction includes character recognition, edge detection, and color analysis.
It should be further noted that, the data processing module further performs feature extraction on the overall image information of the plurality of electric meters on the tray captured by the 3D camera in the three-dimensional point cloud model based on the SIFT algorithm, performs gaussian blur operation on the three-dimensional overall image information, uses the DoG to detect local extremum points in the scale space after constructing the gaussian pyramid, and calculates the gradient direction around each key point as the key point；
I is point cloud data, and x, y and z are key point coordinates;
obtaining a gradient direction histogram with the size of n, connecting the gradient direction histogram into a vector, and using the vector as a description vector set of key pointsD：Wherein->Represent the firstiGradient histogram vectors for the sub-regions;
calculating the distance between descriptors of key points by adopting a neighbor matching method, selecting the descriptors closest to the key points as matching points, and estimating the actual pose of each ammeter in the whole image information by adopting a RANSAC;
and then, using the set of matching point pairs as the input of the RANSAC, finding an inner point set which is most in line with the geometric transformation through an iterative process, and estimating the final geometric transformation pose of the ammeter.
And comparing the final geometrical transformation pose of the electric meter with a preset geometrical transformation pose of the electric meter, and judging whether the requirements of the placement pose are met.
It should be further noted that, if the data processing module compares and judges that the LCD screen, the sign character, the bar code or the LED indicator of the electric meter is not matched with the image information of the standard electric meter, the PLC industrial personal computer controls the pneumatic clamping unit to grasp the unmatched electric meter and convey to the manual processing area.
From the above technical scheme, the invention has the following advantages:
the fault processing system applied to the intelligent ammeter automatic detection line provided by the invention is used for judging whether the pose information of all the ammeter is matched with the pose information of each ammeter in a preset standard image or not by comparing the pose information of each ammeter in the whole image information with the pose information of each ammeter in the preset standard image; if the electric meters are not matched, the information of the placing pose of the electric meters can be obtained, the pneumatic clamping unit is controlled to grasp the unmatched electric meters, and the placing direction is adjusted, so that the information of the placing pose of the electric meters meets the technological requirements.
The invention can also preprocess the placing pose information of each ammeter in the whole image information based on a point cloud data processing mode, remove noise points, downsampling processing and the like to reduce noise and data quantity, segment the point cloud data related to each ammeter pose information, and extract the ammeter pose information so as to facilitate subsequent comparison and judgment, thereby improving the efficiency and accuracy of comparison and judgment.
The invention can also detect the state information of the LCD screen, the signage characters, the bar codes and the LED indicator lamps of the ammeter, judge whether the production process and the quality detection requirement of the ammeter are met, grasp the ammeter with abnormal or unprinted signage characters and bar codes, and convey the ammeter to a manual processing area for subsequent manual processing, thereby ensuring the quality of the ammeter.
According to the invention, visual analysis results are obtained by analyzing the visual data, so that the accuracy of detecting and positioning the ammeter image is improved, and the ammeter production efficiency is improved.
Drawings
In order to more clearly illustrate the technical solutions of the present invention, the drawings that are needed in the description will be briefly introduced below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic diagram of a fault handling system applied to an automated inspection line of a smart meter.
Detailed Description
The invention provides a fault processing system applied to an automatic detection line of an intelligent ammeter, and relates to an ammeter detection line, a PLC (programmable logic controller), a cooperative robot and a pneumatic clamping unit. The system has a wired or wireless communication network therein for providing a medium for communication links between the PLC industrial personal computer, the cooperating robot and the pneumatic clamping unit. The network may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.
It should be understood that the number of PLC computers, co-robots, and pneumatic clamping units in fig. 1 is merely illustrative. There may be any number of trays, co-operating robots, and pneumatic gripping units, as desired. For example, the server may be a server cluster formed by a plurality of servers.
The PLC industrial personal computer can comprise a wireless communication module, a data acquisition module, a data processing module, a data storage module, a data display module, a user input module, a sensing module, an interface module, a power module and the like. It should be understood that not all illustrated components may be required to be implemented. More or fewer components may be implemented instead.
The data processing module may include a central processing unit that may perform various appropriate actions and processes according to programs stored in the data storage module or programs loaded from a storage portion into a random access memory (RAM, random Access Memory). In the RAM, various programs and data required for the system operation are also stored.
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, a schematic diagram of a fault handling system applied to an automated inspection line of a smart meter according to an embodiment of the present invention is shown, the system includes: ammeter detection line, PLC industrial computer, cooperation robot and pneumatic clamping unit.
In this embodiment, the electric meter verification line is provided with a plurality of trays, and the electric meter verification line may adopt belt transmission or chain transmission to drive the plurality of trays to move horizontally.
A plurality of ammeter are arranged on the tray; the ammeter is put on the tray based on a preset putting mode, and the surface of the ammeter faces upwards. The placement can be performed manually or automatically by a robot. The plurality of electricity meters placed on the tray may be arranged in a matrix, for example, in a 4 x 4 manner, or in a 3 x 3 manner.
The electric meter verification line is provided with a detection position, and the cooperative robot and the pneumatic clamping unit are arranged close to the detection position; the verification position is provided with a proximity switch; the PLC industrial personal computer is connected with the proximity switch to acquire a trigger signal when the tray approaches the proximity switch, and controls the cooperative robot to drive the visual sensing unit to move to the position above the verification tray. That is, any tray can be operated to the detection position to trigger the proximity switch, so that the PLC industrial personal computer can learn the operation position of the tray, and the acquisition and collection of the ammeter information on the tray are realized.
In the embodiment, a visual sensing unit is arranged on the cooperative robot; specifically, the cooperative robot is provided with a mechanical arm, and the tail end of the mechanical arm is provided with a visual sensing unit and an attitude sensor; the gesture sensor can sense the operation gesture information of the mechanical arm, and the bottom of the cooperative robot is provided with a base.
The vision sensing unit includes: 3D cameras and 2D cameras; it can be understood that the 3D camera is used for capturing the whole image information of the plurality of electric meters on the tray, and takes the three-dimensional point cloud image as the whole image information; the 2D camera is used for shooting upper surface image information of a plurality of ammeter on the tray. The whole image information is used for judging the placing position of the ammeter on the tray, and whether the placing gesture meets the production process or not. For example, the electric meters on the trays need to be uniformly placed towards a preset direction, so that the robots in the subsequent procedures can conveniently grasp and transport the electric meters, and the subsequent production can be smoothly carried out. If the electric meters on the tray are not arranged in a preset direction, for example, the electric meters should be arranged in a direction which faces the running direction of the electric meter detection line, and one electric meter faces the opposite direction of the running direction of the electric meter detection line, the whole image information shot by the 3D camera is analyzed, and the electric meter is obtained. The electric meters are arranged to protrude from other electric meters, possibly due to overlapping, which can also be obtained by analyzing based on the whole image information.
The 2D camera can be used for judging whether the LCD screen, the signage characters, the bar codes and the LED indicator lamps of the electric meters are complete or not and whether the image information of the upper surfaces of the electric meters on the tray is at a preset position or not. If a certain ammeter is marked with a sign character which is not marked or the bar code is in a wrong position, the identification can be carried out.
According to the embodiment of the application, the PLC industrial personal computer is connected with the cooperative robot, so that the cooperative robot is controlled to drive the visual sensing unit to move to the position detection tray, the visual sensing unit is controlled to capture the whole image information of the plurality of electric meters on the tray, the PLC industrial personal computer compares the position and posture information of each electric meter in the whole image information with the position and posture information of each electric meter in the preset standard image, and whether the position and posture information of all the electric meters are matched with the position and posture information of each electric meter in the preset standard image is judged;
the placing pose information of the electric meters is the position of each electric meter placed on the tray, and the electric meters are required to be uniformly oriented in a preset direction under normal conditions. If the placing pose information of the electric meters is not matched, the PLC industrial personal computer controls the pneumatic clamping unit to grasp the unmatched electric meters, and adjusts the placing pose of the electric meters in the tray, so that the adjusted placing pose of the electric meters is matched with the preset placing pose information. The method is based on the fact that the PLC is used for judging whether the placing pose information of all the electric meters is matched with the placing pose information of each electric meter in a preset standard image or not by comparing the placing pose information of each electric meter in the whole image information with the placing pose information of each electric meter in the preset standard image; if the electric meters are not matched, the information of the placing pose of the electric meters can be obtained, the pneumatic clamping unit is controlled to grasp the unmatched electric meters, and the placing direction is adjusted, so that the information of the placing pose of the electric meters meets the technological requirements.
In one exemplary embodiment, the position of the manipulator arm of the cooperative robot, the position of the pneumatic clamping unit and the position of the ammeter may be processed based on the point cloud data in the system. According to the embodiment, the position information of the mechanical arm of the cooperative robot, the position information of the pneumatic clamping unit and the position information of the ammeter can be positioned with high precision, high resolution and high dimensionality based on the point cloud data, the control is effectively performed, and the pose information and the surface information of the ammeter can be intuitively represented.
The PLC industrial personal computer of the embodiment may further process the point cloud data related to the electric meter pose information according to the area to which the point cloud data belongs based on the point cloud data processing manner, for example, may perform preprocessing on the pose information of each electric meter in the whole image information, remove noise, downsampling, and so on, so as to reduce noise and data quantity, partition out the point cloud data related to each electric meter pose information, and extract the electric meter pose information, so that the subsequent comparison and judgment are convenient, and the efficiency and accuracy of the comparison and judgment are improved.
The integral image information preprocessed based on the point cloud data can be processed by using a deep learning model such as a Convolutional Neural Network (CNN), so that the fault processing efficiency and accuracy of the automatic detection line of the intelligent ammeter are improved.
As an implementation mode of the invention, the PLC acquires pose coordinates according to the pose sensor at the tail end of the mechanical arm, converts the pose coordinates into a robot base coordinate system, and calibrates the coordinate system conversion relation as follows:（1）
wherein,for visual sense unit to robot arm end conversion matrix, < >>For calibrating the conversion matrix of board to cooperation robot base, +.>To coordinate the robot base to robot arm tip conversion matrix,the matrix is a conversion matrix from the visual sensing unit to the calibration plate.
The calibration plate is fixed close to the base of the cooperative robot, the setting position of the calibration plate is in the visual field range of the visual sensing unit, and the visual sensing unit shoots the whole image information when shooting the whole image information, and the whole image information is taken as a reference object.
The PLC industrial personal computer controls the cooperative robot to change the pose, and the method comprises the following steps of:
(2)
(3)
for the first time point calibration plate to the co-operating robot base conversion matrix, < >>Calibrating a conversion matrix from the plate to the base of the cooperative robot for a second time point; />For the transformation matrix from the first time point cooperation robot base to the tail end of the mechanical arm, < >>A conversion matrix from the base of the cooperative robot to the tail end of the mechanical arm is used for a second time point; />For the first time point the conversion matrix of the visual sensor unit to the calibration plate,/for the first time point the visual sensor unit to the calibration plate>For the conversion matrix of the second time point vision sensor unit to the calibration plate, equation (1) and equation (2) are combined to determine +.>. The second point in time here is a point in time subsequent to the first point in time. The time interval is arranged between the first time point and the second time point, the specific time interval is not limited, and the time interval can be set according to actual needs.
According to the embodiment of the application, the 3D image is subjected to point cloud filtering, denoising, feature extraction and electric meter pose estimation, and is matched and compared with the pose information of each electric meter in the preset standard image, if the pose information of the electric meters is not matched, the position coordinates of the electric meters with the unmatched pose information are obtained by utilizingUnder the coordinate system of the base of the cooperation robot, the electric meter is extracted from the tray in the arrangement pose, the arrangement position of the electric meter is extracted, the electric meter can be obtained by mismatching with the information of the preset arrangement pose, and the arrangement pose is grasped and adjusted through the pneumatic clamping unit, so that the requirement of the arrangement pose is met.
According to another embodiment of the invention, after the conversion to the coordinate system of the base of the cooperative robot, the data processing module further performs feature extraction on the whole image information of the plurality of electric meters on the tray, which is shot by the 3D camera, in the three-dimensional point cloud model based on the SIFT algorithm, performs Gaussian blur operation on the three-dimensional whole image information, detects local extremum points in the scale space by using the DOG after constructing the Gaussian pyramid as key points, and calculates the surrounding gradient direction for each key point。
I is point cloud data, and x, y and z are key point coordinates.
Obtaining a gradient direction histogram with the size of n, connecting the gradient direction histogram into a vector, and using the vector as a description vector set of key pointsD：Wherein->Represent the firstiGradient histogram vectors for the sub-regions;ithe value of (2) can be set according to the number of blocks for placing the ammeter on the tray.
Calculating the distance between descriptors of key points by adopting a neighbor matching method, selecting the descriptors closest to the key points as matching points, and estimating the actual pose of each ammeter in the whole image information by adopting a RANSAC;
and then, using the set of matching point pairs as the input of the RANSAC, finding an inner point set which is most in line with the geometric transformation through an iterative process, and estimating the final geometric transformation pose of the ammeter.
And comparing the final geometrical transformation pose of the electric meter with a preset geometrical transformation pose of the electric meter, and judging whether the requirements of the placement pose are met.
If the placing pose information of the electric meters is not matched, the PLC industrial personal computer controls the pneumatic clamping unit to grasp the unmatched electric meters, and adjusts the placing pose of the electric meters in the tray, so that the adjusted placing pose of the electric meters is matched with the preset placing pose information.
For the point cloud processing mode in the embodiment, the setting pose information of each ammeter in the whole image information can be realized, and the result output is realized based on the point cloud feature extraction and setting pose detection. And in the whole image information processing process, the operations of removing noise, sampling, filtering and the like are also involved. The noise removal can be realized by a statistical method, curvature estimation and the like, and the sampling and filtering can reduce redundant information and noise interference of the point cloud data. The feature can be extracted through geometrical and topological properties of the point cloud by extracting the pose information of each ammeter in the whole image information, and common methods comprise shape-based features, normal vector-based features, surface curvature-based features and the like. These features may be used to describe pose information, shape information, size information, direction information, etc. of each meter in the overall image information.
In this embodiment, the pose information of each ammeter in the whole image information may be detected by deep learning, or the like, and may of course also include a 2D projection-based method, a 3D frame-based method, a point cloud segmentation-based method, and the like. The information of the placement pose of each detected ammeter can be output and displayed in a three-dimensional frame or point cloud semantic segmentation mode, so that the detection accuracy and efficiency are improved.
It can be seen that, in this embodiment, by comparing the pose information of each electric meter in the overall image information with the pose information of each electric meter in the preset standard image, that is, comparing the point of the pose information of each electric meter in the overall image information with the point of the pose information of each electric meter in the preset standard image, the relative pose transformation between the two point cloud data can be estimated by using a common transformation model (such as rigid transformation, affine transformation, non-rigid transformation, etc.). In transform estimation, the transform parameters are typically solved using a least squares method or a maximum likelihood method. According to the estimated transformation parameters, one point cloud data is transformed into the other point cloud data under the coordinate system, so that the two point cloud data are aligned under the same coordinate system, and the comparison of the placement pose information of each ammeter is realized.
According to the embodiment of the application, the data acquisition module is further used for acquiring the upper surface image information of the plurality of ammeter on the 2D camera shooting tray; the data processing module is used for sequentially carrying out image noise reduction, image enhancement and feature extraction on the upper surface image information; extracting an LCD screen, signage characters, bar codes and LED indicator lamps of the ammeter; the feature extraction includes character recognition, edge detection, and color analysis. The data processing module is used for respectively and correspondingly comparing the LCD screen, the signage characters, the bar codes and the LED indicator lamps of the ammeter with the image information of the standard ammeter to judge whether the images are matched; the data storage module is used for storing the acquired upper surface image information, the standard ammeter image information and the comparison judgment information; if the data processing module compares and judges that the LCD screen, the signage characters, the bar codes or the LED indicator lamps of the electric meter are not matched with the image information of the standard electric meter, the PLC industrial personal computer controls the pneumatic clamping unit to grab the unmatched electric meter and convey the electric meter to the manual processing area. The data display module is used for displaying upper surface image information and comparison judgment information result information.
Here, the points of the image information of the standard ammeter and the points of the image information of the upper surfaces of the plurality of ammeters on the uptake tray are also compared, and a common transformation model (such as rigid transformation, affine transformation, non-rigid transformation and the like) can be used for estimating the relative posture transformation between the two point cloud data. In transform estimation, the transform parameters are typically solved using a least squares method or a maximum likelihood method. According to the estimated transformation parameters, one point cloud data is transformed into the other point cloud data under the coordinate system, so that the two point cloud data are aligned under the same coordinate system, and the comparison of the points of the standard ammeter image information and the points of the upper surface image information of the ammeter is realized.
The embodiment can also realize the defect detection of LCD screens, signage characters, bar codes and LED indicator lamps of the electric meter by utilizing median filtering, binarization, edge detection, template matching, OCR and other image processing technologies.
Like this, the system of this embodiment can detect LCD screen, sign character, bar code and the state information of LED pilot lamp of ammeter, judges whether to satisfy the quality detection requirement of production technology and ammeter, snatchs the ammeter that appears unusual or does not print sign character and bar code, conveys to artifical processing area to follow-up by the manual work, guarantee the quality of ammeter.
The units and algorithm steps of each example described in the embodiments disclosed in the fault handling system applied to the automation line of the smart meter provided by the invention can be implemented in electronic hardware, computer software or a combination of both, and in order to clearly illustrate the interchangeability of hardware and software, the components and steps of each example have been generally described in terms of functions in the above description. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The terms "first," "second," "third," "fourth" and the like in the description and in the claims and in the above drawings, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprise" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. Be applied to fault handling system of smart electric meter automation line of examining, characterized in that includes: the device comprises an ammeter detection line, a PLC industrial personal computer, a cooperative robot and a pneumatic clamping unit;
a plurality of trays are arranged on the ammeter verification line, and a plurality of ammeter are placed on the trays; the electric meter verification line is provided with a detection position, and the cooperative robot and the pneumatic clamping unit are arranged close to the detection position;
the cooperative robot is provided with a visual sensing unit;
the PLC industrial personal computer is connected with the cooperative robot, controls the cooperative robot to drive the visual sensing unit to move above the verification position tray, controls the visual sensing unit to capture the whole image information of a plurality of electric meters on the tray, compares the placement pose information of each electric meter in the whole image information with the placement pose information of each electric meter in a preset standard image, and judges whether the placement pose information of all the electric meters is matched with the placement pose information of each electric meter in the preset standard image;
if the placing pose information of the electric meters is not matched, the PLC industrial personal computer controls the pneumatic clamping unit to grasp the unmatched electric meters, and adjusts the placing pose of the electric meters in the tray, so that the adjusted placing pose of the electric meters is matched with the preset placing pose information.
2. The fault handling system for a smart meter automated inspection line of claim 1, wherein the inspection site is provided with a proximity switch;
the PLC industrial personal computer is connected with the proximity switch to acquire a trigger signal when the tray approaches the proximity switch, and controls the cooperative robot to drive the visual sensing unit to move to the position above the verification tray.
3. The fault handling system applied to the intelligent ammeter automation test line according to claim 1, wherein the cooperative robot senses position information based on point cloud data and controls a visual sensing unit to capture integral image information of a plurality of ammeter on the tray above the tray based on a control instruction of a PLC (programmable logic controller) industrial personal computer.
4. The fault handling system for a smart meter automation line of claim 3, wherein the vision sensing unit comprises: 3D cameras and 2D cameras;
the 3D camera is used for shooting the whole image information of the plurality of ammeter on the tray, and the three-dimensional point cloud image is used as the whole image information;
the 2D camera is used for shooting upper surface image information of a plurality of ammeter on the tray.
5. The fault handling system for an automated inspection line of a smart meter of claim 4, wherein the collaborative robot is provided with a robotic arm, and a vision sensing unit and an attitude sensor are disposed at a distal end of the robotic arm;
the bottom of the cooperative robot is provided with a base;
the PLC industrial personal computer acquires pose coordinates according to the pose sensor, converts the pose coordinates into a robot base coordinate system, and calibrates the coordinate system conversion relation as follows:
（1）
wherein,for visual sense unit to robot arm end conversion matrix, < >>For calibrating the conversion matrix of board to cooperation robot base, +.>For the transformation matrix of the co-operating robot base to the end of the robot arm +.>The matrix is a conversion matrix from the visual sensing unit to the calibration plate.
6. The fault handling system for the automatic detection line of the intelligent ammeter according to claim 5, wherein the PLC is used for controlling the cooperative robot to change the pose, and the following steps are obtained:
(2)
(3)
for the first time point calibration plate to the co-operating robot base conversion matrix, < >>Calibrating a conversion matrix from the plate to the base of the cooperative robot for a second time point; />For the transformation matrix from the first time point cooperation robot base to the tail end of the mechanical arm, < >>A conversion matrix from the base of the cooperative robot to the tail end of the mechanical arm is used for a second time point; />For the first time point the conversion matrix of the visual sensor unit to the calibration plate,/for the first time point the visual sensor unit to the calibration plate>And (3) converting the visual sensing unit to a calibration plate for a second time point.
7. The fault handling system for a smart meter automation line of claim 4, wherein the PLC comprises: the device comprises a data acquisition module, a data processing module, a data storage module and a data display module;
the data acquisition module is used for acquiring image information of the upper surfaces of the plurality of ammeter on the 2D camera shooting tray;
the data processing module is used for sequentially carrying out image noise reduction, image enhancement and feature extraction on the upper surface image information;
extracting an LCD screen, signage characters, bar codes and LED indicator lamps of the ammeter;
the data processing module is used for respectively and correspondingly comparing the LCD screen, the signage characters, the bar codes and the LED indicator lamps of the ammeter with the image information of the standard ammeter to judge whether the images are matched;
the data storage module is used for storing the acquired upper surface image information, the standard ammeter image information and the comparison judgment information;
the data display module is used for displaying upper surface image information and comparison judgment information result information.
8. The fault handling system for a smart meter automation line of claim 7, wherein the feature extraction includes character recognition, edge detection, and color analysis.
9. The fault handling system for automatic detection line of intelligent ammeter according to claim 7, wherein the data processing module further performs feature extraction on the whole image information of a plurality of ammeter on the tray captured by the 3D camera in a three-dimensional point cloud model based on SIFT algorithm, performs gaussian blur operation on the whole image information in three dimensions, detects local extremum points in a scale space by using DoG after constructing gaussian pyramid as key points, and calculates surrounding gradient directions for each key point；
I is point cloud data, and x, y and z are key point coordinates;
obtaining a gradient direction histogram with the size of n, connecting the gradient direction histogram into a vector, and using the vector as a description vector set of key pointsD：Wherein->Represent the firstiGradient histogram vectors for the sub-regions;
calculating the distance between descriptors of key points by adopting a neighbor matching method, selecting the descriptors closest to the key points as matching points, and estimating the actual pose of each ammeter in the whole image information by adopting a RANSAC;
then, a set of matching point pairs is used as an input of the RANSAC, an inner point set which is most in line with geometric transformation is found through an iterative process, and the final geometric transformation pose of the ammeter is estimated;
and comparing the final geometrical transformation pose of the electric meter with a preset geometrical transformation pose of the electric meter, and judging whether the requirements of the placement pose are met.
10. The fault handling system for the automatic check line of the intelligent electric meter according to claim 7, wherein if the data processing module compares and judges that the LCD screen, the signage character, the bar code or the LED indicator lamp of the electric meter is not matched with the image information of the standard electric meter, the PLC industrial personal computer controls the pneumatic clamping unit to grab the unmatched electric meter and convey the unmatched electric meter to the manual processing area.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410295705.4A CN117890851A (en) | 2024-03-15 | 2024-03-15 | Fault processing system applied to automatic detection line of intelligent ammeter |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410295705.4A CN117890851A (en) | 2024-03-15 | 2024-03-15 | Fault processing system applied to automatic detection line of intelligent ammeter |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117890851A true CN117890851A (en) | 2024-04-16 |
Family
ID=90639730
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410295705.4A Pending CN117890851A (en) | 2024-03-15 | 2024-03-15 | Fault processing system applied to automatic detection line of intelligent ammeter |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117890851A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH11123681A (en) * | 1997-10-24 | 1999-05-11 | Mitsubishi Electric Corp | Picking-up device and picking-up method |
| CN205211156U (en) * | 2015-12-09 | 2016-05-04 | 山东正煦电气有限公司 | A yard device is tested to full -automatic ammeter intelligence |
| CN111983546A (en) * | 2020-08-26 | 2020-11-24 | 国网山东省电力公司营销服务中心(计量中心) | Ammeter detection configuration device and method |
| CN113112694A (en) * | 2021-04-29 | 2021-07-13 | 江苏云舜能源科技有限公司 | Power grid intelligent terminal cabinet capable of being stored and taken quickly and using method thereof |
| CN114236457A (en) * | 2021-11-16 | 2022-03-25 | 云南电网有限责任公司 | Electric energy meter detection logistics scheduling control system and method |
| CN115061078A (en) * | 2022-06-21 | 2022-09-16 | 安徽南瑞中天电力电子有限公司 | Cloud platform based electric energy meter online automatic detection system and detection method thereof |
-
2024
- 2024-03-15 CN CN202410295705.4A patent/CN117890851A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH11123681A (en) * | 1997-10-24 | 1999-05-11 | Mitsubishi Electric Corp | Picking-up device and picking-up method |
| CN205211156U (en) * | 2015-12-09 | 2016-05-04 | 山东正煦电气有限公司 | A yard device is tested to full -automatic ammeter intelligence |
| CN111983546A (en) * | 2020-08-26 | 2020-11-24 | 国网山东省电力公司营销服务中心(计量中心) | Ammeter detection configuration device and method |
| CN113112694A (en) * | 2021-04-29 | 2021-07-13 | 江苏云舜能源科技有限公司 | Power grid intelligent terminal cabinet capable of being stored and taken quickly and using method thereof |
| CN114236457A (en) * | 2021-11-16 | 2022-03-25 | 云南电网有限责任公司 | Electric energy meter detection logistics scheduling control system and method |
| CN115061078A (en) * | 2022-06-21 | 2022-09-16 | 安徽南瑞中天电力电子有限公司 | Cloud platform based electric energy meter online automatic detection system and detection method thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113610921B (en) | Hybrid workpiece gripping method, apparatus, and computer readable storage medium | |
| CN107389701A (en) | A kind of PCB visual defects automatic checkout system and method based on image | |
| CN110246127A (en) | Workpiece identification and localization method and system, sorting system based on depth camera | |
| CN114952809A (en) | Workpiece identification and pose detection method and system and grabbing control method of mechanical arm | |
| Lin | Development of an intelligent transformer insertion system using a robot arm | |
| CN113269723A (en) | Unordered grasping system for three-dimensional visual positioning and mechanical arm cooperative work parts | |
| Wu et al. | An end-to-end learning method for industrial defect detection | |
| CN113780484B (en) | Industrial product defect detection method and device | |
| CN113705564B (en) | Pointer type instrument identification reading method | |
| CN113706455B (en) | Rapid detection method for damage of 330kV cable porcelain insulator sleeve | |
| CN113269234B (en) | Connecting piece assembly detection method and system based on target detection | |
| CN114331961A (en) | Method for defect detection of an object | |
| CN110570398A (en) | Cable joint welding spot qualification detection method based on deep learning technology | |
| CN114332622A (en) | Label detection method based on machine vision | |
| CN114219753A (en) | Power equipment surface defect detection method based on deep learning and terminal | |
| CN112763496A (en) | Mobile phone battery surface defect detection device and detection method thereof | |
| CN117890851A (en) | Fault processing system applied to automatic detection line of intelligent ammeter | |
| Frank et al. | Stereo-vision for autonomous industrial inspection robots | |
| Ying et al. | Pose Estimation of a Small Connector Attached to the Tip of a Cable Sticking Out of a Circuit Board | |
| CN114266822A (en) | Workpiece quality inspection method and device based on binocular robot, robot and medium | |
| Qian et al. | The autonomous detection of sheet metal parts using imageprocessing | |
| CN113112458A (en) | Metal surface defect detection method based on support vector machine | |
| CN109298314A (en) | Circuit board port connect-disconnect life test macro and method based on image procossing | |
| CN116572253B (en) | Grabbing control method and device for test tube | |
| TWI772181B (en) | Automatic recognizing system and automatic recognizing method for a pick-up position of a printed circuit board |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |